Cargando…

Deep learning approach to peripheral leukocyte recognition

Microscopic examination of peripheral blood plays an important role in the field of diagnosis and control of major diseases. Peripheral leukocyte recognition by manual requires medical technicians to observe blood smears through light microscopy, using their experience and expertise to discriminate...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Qiwei, Bi, Shusheng, Sun, Minglei, Wang, Yuliang, Wang, Di, Yang, Shaobao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6592546/
https://www.ncbi.nlm.nih.gov/pubmed/31237896
http://dx.doi.org/10.1371/journal.pone.0218808
_version_ 1783429906184536064
author Wang, Qiwei
Bi, Shusheng
Sun, Minglei
Wang, Yuliang
Wang, Di
Yang, Shaobao
author_facet Wang, Qiwei
Bi, Shusheng
Sun, Minglei
Wang, Yuliang
Wang, Di
Yang, Shaobao
author_sort Wang, Qiwei
collection PubMed
description Microscopic examination of peripheral blood plays an important role in the field of diagnosis and control of major diseases. Peripheral leukocyte recognition by manual requires medical technicians to observe blood smears through light microscopy, using their experience and expertise to discriminate and analyze different cells, which is time-consuming, labor-intensive and subjective. The traditional systems based on feature engineering often need to ensure successful segmentation and then manually extract certain quantitative and qualitative features for recognition but still remaining a limitation of poor robustness. The classification pipeline based on convolutional neural network is of automatic feature extraction and free of segmentation but hard to deal with multiple object recognition. In this paper, we take leukocyte recognition as object detection task and apply two remarkable object detection approaches, Single Shot Multibox Detector and An Incremental Improvement Version of You Only Look Once. To improve recognition performance, some key factors involving these object detection approaches are explored and the detection models are generated using the train set of 14,700 annotated images. Finally, we evaluate these detection models on test sets consisting of 1,120 annotated images and 7,868 labeled single object images corresponding to 11 categories of peripheral leukocytes, respectively. A best mean average precision of 93.10% and mean accuracy of 90.09% are achieved while the inference time is 53 ms per image on a NVIDIA GTX1080Ti GPU.
format Online
Article
Text
id pubmed-6592546
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-65925462019-07-05 Deep learning approach to peripheral leukocyte recognition Wang, Qiwei Bi, Shusheng Sun, Minglei Wang, Yuliang Wang, Di Yang, Shaobao PLoS One Research Article Microscopic examination of peripheral blood plays an important role in the field of diagnosis and control of major diseases. Peripheral leukocyte recognition by manual requires medical technicians to observe blood smears through light microscopy, using their experience and expertise to discriminate and analyze different cells, which is time-consuming, labor-intensive and subjective. The traditional systems based on feature engineering often need to ensure successful segmentation and then manually extract certain quantitative and qualitative features for recognition but still remaining a limitation of poor robustness. The classification pipeline based on convolutional neural network is of automatic feature extraction and free of segmentation but hard to deal with multiple object recognition. In this paper, we take leukocyte recognition as object detection task and apply two remarkable object detection approaches, Single Shot Multibox Detector and An Incremental Improvement Version of You Only Look Once. To improve recognition performance, some key factors involving these object detection approaches are explored and the detection models are generated using the train set of 14,700 annotated images. Finally, we evaluate these detection models on test sets consisting of 1,120 annotated images and 7,868 labeled single object images corresponding to 11 categories of peripheral leukocytes, respectively. A best mean average precision of 93.10% and mean accuracy of 90.09% are achieved while the inference time is 53 ms per image on a NVIDIA GTX1080Ti GPU. Public Library of Science 2019-06-25 /pmc/articles/PMC6592546/ /pubmed/31237896 http://dx.doi.org/10.1371/journal.pone.0218808 Text en © 2019 Wang et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Wang, Qiwei
Bi, Shusheng
Sun, Minglei
Wang, Yuliang
Wang, Di
Yang, Shaobao
Deep learning approach to peripheral leukocyte recognition
title Deep learning approach to peripheral leukocyte recognition
title_full Deep learning approach to peripheral leukocyte recognition
title_fullStr Deep learning approach to peripheral leukocyte recognition
title_full_unstemmed Deep learning approach to peripheral leukocyte recognition
title_short Deep learning approach to peripheral leukocyte recognition
title_sort deep learning approach to peripheral leukocyte recognition
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6592546/
https://www.ncbi.nlm.nih.gov/pubmed/31237896
http://dx.doi.org/10.1371/journal.pone.0218808
work_keys_str_mv AT wangqiwei deeplearningapproachtoperipheralleukocyterecognition
AT bishusheng deeplearningapproachtoperipheralleukocyterecognition
AT sunminglei deeplearningapproachtoperipheralleukocyterecognition
AT wangyuliang deeplearningapproachtoperipheralleukocyterecognition
AT wangdi deeplearningapproachtoperipheralleukocyterecognition
AT yangshaobao deeplearningapproachtoperipheralleukocyterecognition